Difan Zou

papers

243

total citations

papers (11)

How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?

ICLR 2024arXiv

citations

Parallelized Autoregressive Visual Generation

CVPR 2025arXiv

citations

The Benefits of Implicit Regularization from SGD in Least Squares Problems

NEURIPS 2021arXiv

citations

The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift

NEURIPS 2022arXiv

citations

What Can Transformer Learn with Varying Depth? Case Studies on Sequence Learning Tasks

ICML 2024arXiv

citations

Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference

ICML 2024arXiv

citations

Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning

NEURIPS 2025arXiv

citations

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks

NEURIPS 2025arXiv

citations

Difan Zou

papers (11)

How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?

Parallelized Autoregressive Visual Generation

The Benefits of Implicit Regularization from SGD in Least Squares Problems

The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift

What Can Transformer Learn with Varying Depth? Case Studies on Sequence Learning Tasks

Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference

Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data

Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime

Faster Sampling via Stochastic Gradient Proximal Sampler

Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks

papers (11)

How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?

Parallelized Autoregressive Visual Generation

The Benefits of Implicit Regularization from SGD in Least Squares Problems

The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift

What Can Transformer Learn with Varying Depth? Case Studies on Sequence Learning Tasks

Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference

Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data

Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime

Faster Sampling via Stochastic Gradient Proximal Sampler

Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks